Model comparison
Claude 3 Haiku vs Gemma 7B
Gemma 7B is the stronger model overall, scoring 29.5 to 25.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
GoogleSummary
- They share 18 benchmarks with published results for both. Claude 3 Haiku scores higher in 4 categories and Gemma 7B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 7B leads 28.7 to 9.2.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Haiku | Gemma 7B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 25.7 | 29.5 |
| Released | 2024-03-07 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 37 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 7B leads
Claude 3 Haiku: 26.1 (#320), Gemma 7B: 29.9 (#290)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Coding | 1199 | 1048 |
| HumanEval+ | 68.9% | 28.7% |
| MBPP+ | 68.8% | 43.4% |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
Reasoning Gemma 7B leads
Claude 3 Haiku: 15.7 (#303), Gemma 7B: 19.0 (#247)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1042 |
| Epoch Capabilities Index | 118.3 | 111.74 |
| WinoGrande | 74.2% | 79% |
| Kagi LLM Benchmark | 34.2% | — |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| ForecastBench | 53.2 | — |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
Math Gemma 7B leads
Claude 3 Haiku: 9.2 (#313), Gemma 7B: 28.7 (#225)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Math | 1188 | 1066 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |
| GSM8K | — | 46.4% |
Knowledge Gemma 7B leads
Claude 3 Haiku: 17.3 (#280), Gemma 7B: 26.8 (#248)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Expert | 1148 | 1002 |
| MMLU | 73.8% | 66.1% |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 83.2% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multimodal Not comparable
Claude 3 Haiku: 23.1 (#123), Gemma 7B: —
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |
Multilingual Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#238), Gemma 7B: 25.3 (#282)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1178 | 999 |
| LMArena Chinese | 1155 | 1035 |
| LMArena French | 1194 | 1024 |
| LMArena Russian | 1204 | 993 |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1108 | — |
| LMArena Spanish | 1165 | — |
Instruction Following Claude 3 Haiku leads
Claude 3 Haiku: 61.5 (#242), Gemma 7B: 51.7 (#290)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1174 | 1017 |
Long Context Claude 3 Haiku leads
Claude 3 Haiku: 36.1 (#232), Gemma 7B: 31.1 (#277)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Longer Query | 1191 | 1022 |
Writing & Preference Claude 3 Haiku leads
Claude 3 Haiku: 29.8 (#286), Gemma 7B: 27.2 (#297)
| Benchmark | Claude 3 Haiku | Gemma 7B |
|---|---|---|
| LMArena Text | 1195 | 1056 |
| LMArena Creative Writing | 1157 | 1024 |
| LMArena Multi-Turn | 1190 | 963 |
| EQ-Bench Creative Writing | 717 | — |
Frequently asked questions
Is Claude 3 Haiku better than Gemma 7B?
Gemma 7B is the stronger model overall, scoring 29.5 to 25.7 on the Noometry Index.
Is Claude 3 Haiku or Gemma 7B better for coding?
Gemma 7B scores higher on coding benchmarks: 29.9 versus 26.1 in the Noometry coding category.
How many benchmarks do Claude 3 Haiku and Gemma 7B share?
18 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Gemma 7B has 27.